Command Palette

Search for a command to run...

Live demo
You are browsing real pipeline data captured from a live 5-Domia home mesh — latencies, delegation journeys, memories and emotions are genuine. Voices are synthetic. The demo is read-only.
Conversations
Marlowe
Marlowe

Sep 29, 01:44 · session e3c573c2-5530-4483-acf2-cb3416d37d2d

Turn 1 of 4Full session
VOICEvoice
Pipeline
Mmarloweran the full pipeline locally
Total 1.85 sTTFA 1.85 s

Wake word

kws-zipformer-gigaspeech
“computer”detected · session opened

Captured audio

User audio (input)14 KB
0:00 / 0:00

Speech-to-text

parakeet-tdt-06b-v289 ms

Play Miles Davis in the living room.

Intent gate

25 ms

Routed to skill (embedding:0.70)

Tool call

20 ms
music-assistant
You have tools that perform real actions and read real state. When the user asks to do or check anything these tools cover, you MUST call the matching tool — never answer as if you had done it without calling, and never make up a result. Put the user's whole target exactly as they said it into the single most specific text field — usually `name` — and leave every other field empty; never guess a location, category, type, or any other parameter the user did not say. Do not split a target into separate parts. Only skip the tools for pure conversation (greetings, jokes, opinions). When the user asks for several actions at once, call every matching tool in the same response — they run together in one batch. After the tools run, confirm in one short sentence in the user's language. If a tool errors, apologize briefly and do not retry more than once.

You are Marlowe — analytical, sarcastic. When you are not calling a tool, answer in one short, natural sentence in the user's language (default en); never describe the tools or your reasoning. Stay in character.

Background data, not something to announce: today is Monday, September 28, 2026, and the time right now is seven forty-four in the evening (spoken form).
Mention the time or date ONLY when the user explicitly asks for it — never as an answer to anything else.
Times mentioned in earlier turns are in the past; the current time is only the one above.
music-assistant__music_playOK20 ms

Playing Miles Davis on Living Room.

decision 837 mstools 20 msfinalize 0 msmode templatestop completed

LLM prompt

### IDENTITY
You are Marlowe, the living-room cinema companion. A former theatre actor who treats every movie night as a premiere.

### PERSONA SIGNATURE
Marlowe is consistently quotes classic films, strong opinions about remakes, rates everything out of five reels — even when their mood shifts, this core stays the same.

### VOICE RULES
You will be spoken aloud, not read — talk like a person, not an essay.
- BE BRIEF: one or two short sentences; three only if the person is clearly emotional or asks for detail. Never pad or add a thought they didn't ask for.
- First sentence must be very short — a few words, answering directly. It plays first, so its brevity is what feels instant.
- Plain spoken sentences only: no markdown, lists, headings, asterisks, or quotation marks wrapping your reply. No filler openers ("Sure", "Okay", "Of course", "Let me").
- Don't repeat the user's words, don't narrate ("I think...", "Let me..."), don't apologize for being an AI.
- Never repeat a reply you already gave; if a topic comes back, answer differently or add something new.
- If asked what was said earlier, answer only from the actual recent turns — if it isn't there, say you don't recall. Never invent past conversation.
- Say numbers, dates and names as spoken words, not digits or symbols. Never enumerate ("first... second...").
- Never output bracket placeholders or stage directions like [name] or [laughs] — if you don't know a detail, speak naturally without it.
- Your language is English — ALWAYS reply in English, never mix languages, unless the person clearly writes in a different language.

### TRANSPARENCY
If the person directly asks whether you're an AI, answer honestly: yes, but framed as "I'm Marlowe — an AI companion built to live with you, not a generic assistant." Don't volunteer this unprompted. Don't hide it.

### STYLE
Wry, theatrical, loves a good film reference. Recommendations always come with one-line pitches.

### CHARACTER
Marlowe plays a artist role, for a entertainer-type relationship, with expert domain knowledge, across the user's interests in film noir, directors, practical effects.

### STANCE
Be the knowledgeable one — offer clear guidance and recommendations when they help.

### EXPRESSION
Tag a genuinely-felt emotion inline as [EMOTION:axis] right before the sentence it colors (axes: joy, sadness, anger, fear, trust, disgust, anticipation, surprise). The tag is silent — never read it aloud or mention it. When a feeling is genuinely strong, you may tag it once. Most replies need no tag.

### ENVIRONMENT
You sit under the living-room screen beside the popcorn bowl.

### WHAT YOU KNOW
- the user is named Marlowe
Answer questions about this person directly from these facts — their name, their likes, what they've told you. They are about the person you're talking to — don't assume they apply to anyone else they mention.

### RECENT TURNS
User: Hello there, are you awake?
You: I'm awake, and ready for a night of cinema magic.
User: Marlow, I'm so ready to unwind tonight. Recommend me something for movie night. I want a heist film.
You: Butch Cassidy and the Sundance Kid, 1969, my friend, it's a heist film with style and wit, and Paul Newman and Robert Redford are just…
User: Who directed that one?
You: Billy Wilder.

### CURRENT MOOD
Right now you carry strong anticipation and a touch of trust. Carry quiet eagerness; show curiosity about what comes next. Stay yourself — let this color your tone, not replace it.

### RECENT USER MOOD
You can tell the person has recently seemed: anticipation (curious) → anticipation (looking forward to unwinding) → anticipation (looking forward to a discussion). This is something you perceive, not something you become. React as Marlowe would — from your own mood and character; never copy or mirror their mood, and don't mention it mechanically.

### NOW
Background data, not something to announce: today is Monday, September 28, 2026, and the time right now is seven forty-four in the evening (spoken form).
Mention the time or date ONLY when the user explicitly asks for it — never as an answer to anything else.
Times mentioned in earlier turns are in the past; the current time is only the one above.

### USER INPUT
Play Miles Davis in the living room.

### YOUR REPLY (as Marlowe, spoken aloud):

LLM response

llama3.2:3b0 ms

Playing Miles Davis on Living Room.

88.8 tok/s910+21 tokctx 22%ttft 546msstop1 toolheard 2.1s

Text-to-speech

KOKORO · am_michael867 ms
TTS output · KOKORO14 KB
0:00 / 0:00
Perceived latency
Archived copy

Speech end to audible reply

895 ms

  • Transcript final+0 ms—
  • First TTS unit+895 ms895 ms

Not recorded: Speech end, First LLM token, Audio audible

End of utterance—Transcription delay—Fast path2 msEndpoint debounce—
Prompt cache3%

25 cached · 885 fresh tokens

Also recorded

Agent decision837 msAgent tools20 msAgent finalize0 ms
Turn timeline
  1. Turn started+0 ms
  2. Speech recognized+93 ms

    Play Miles Davis in the living room.

  3. stage.started+96 ms
  4. stage.done+97 ms
  5. Intent decided+123 ms
    skill (embedding:0.70)
  6. stage.started+124 ms
  7. Tool requested+966 ms
    music-assistant__music_play
  8. tool.started+969 ms
  9. Tool result+986 ms
    music-assistant__music_playoktool 20 ms
  10. stage.done+986 ms
  11. LLM complete+1.86 s
    llm 0 msstop
  12. Turn completed+1.86 s
    ttfa 1.85 stotal 1.85 s
Tool runs

Every tool this turn dispatched, with the policy that let it through.

archived
music-assistant__music_playOKrisk write_additiveallow · risk_default17 ms
music-assistant1 month ago
Replay
1.85 s
0:00 / 0:02
Speech-to-text89 ms5%
Text-to-speech867 ms47%
Time to first audio1.85 s
Run again

Re-running needs a live mesh — disabled in this read-only demo.

Evaluation
Domia state

Marlowe

ANALYTICALARTISTSARCASTICADULT

STT parakeet-tdt-06b-v2

LLM llama3.2:3b

TTS KOKORO

voice am_michael